[None][feat] KV Connector Support for MTP#10932
Conversation
|
Dependent on #9693 |
|
@jthomson04 were you able to verify the changes? |
|
/bot run --disable-fail-fast |
|
PR_Github #33212 [ run ] triggered by Bot. Commit: |
It seems to be correct, but I'm doing a bit more testing to confirm. |
|
PR_Github #33212 [ run ] completed with state
|
|
Did some more testing, and it works. |
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
jthomson04
force-pushed
the
jthomson04/kv-connector-mtp
branch
from
c2026b1 to
a4361dd
Compare
|
/bot run --disable-fail-fast |
📝 WalkthroughWalkthroughChanges enable speculative decoding to work with KV cache connectors by removing a blocking condition and adjusting token scheduling logic to account for draft tokens. The KV connector can now be used when spec_config is present, and scheduling computation is updated to include draft token length. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes 🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (1)
1-2: Update copyright year to include 2025 or 2026.The copyright header shows
2022-2024, but this file is being modified in 2026 with meaningful changes. As per coding guidelines, the copyright year should reflect the latest meaningful modification.Proposed fix
-# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-FileCopyrightText: Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
🧹 Nitpick comments (1)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (1)
314-315: Remove or update the misleading comment.The inline comment states "Specdec with draft tokens is not supported yet," but this code change is explicitly adding support for draft tokens in the scheduling calculation. The comment appears to be stale or contradictory.
If there are remaining limitations, consider updating the comment to describe what specifically is not yet supported. Otherwise, remove the comment.
Proposed fix
- num_scheduled_tokens = 1 + get_draft_token_length( - req) # Specdec with draft tokens is not supported yet. + num_scheduled_tokens = 1 + get_draft_token_length(req)
|
PR_Github #33236 [ run ] triggered by Bot. Commit: |
|
PR_Github #33236 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #33299 [ run ] triggered by Bot. Commit: |
|
PR_Github #33299 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
1 similar comment
|
/bot run --disable-fail-fast |
|
PR_Github #33400 [ run ] triggered by Bot. Commit: |
|
PR_Github #33400 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #33410 [ run ] triggered by Bot. Commit: |
|
PR_Github #33410 [ run ] completed with state |
4 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
Details
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.